# Deep learning electromagnetic inversion with convolutional neural networks

arXiv: https://arxiv.org/abs/1812.10247 · HTML: https://mlsanity.com/paper/1812.10247/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2018.

## Built on by (most cited first, 13 of 13)

- [Efficient Bayesian inference using physics-informed invertible neural networks for inverse problems](https://mlsanity.com/paper/2304.12541/) (2023)
- [Uncertainty Guided Ensemble Self-Training for Semi-Supervised Global Field Reconstruction](https://mlsanity.com/paper/2302.11940/) (2023)
- [A Test-Time Learning Approach to Reparameterize the Geophysical Inverse Problem with a Convolutional Neural Network](https://mlsanity.com/paper/2312.04752/) (2023)
- [Performance of Machine Learning Methods for Gravity Inversion: Successes and Challenges](https://mlsanity.com/paper/2510.09632/) (2025)
- [Learning Neural Operators from Partial Observations via Latent Autoregressive Modeling](https://mlsanity.com/paper/2601.15547/) (2026)
- [Bayesian PINNs for uncertainty-aware inverse problems (BPINN-IP)](https://mlsanity.com/paper/2602.04459/) (2026)
- [Design of borehole resistivity measurement acquisition systems using deep learning](https://mlsanity.com/paper/2101.05623/) (2021)
- [Automated machine learning for borehole resistivity measurements](https://mlsanity.com/paper/2207.09849/) (2022)
- [3-D Magnetotelluric Deep Learning Inversion Guided by Pseudo-Physical Information](https://mlsanity.com/paper/2410.09388/) (2024)
- [Learning Latent Hardening (LLH): Enhancing Deep Learning with Domain Knowledge for Material Inverse Problems](https://mlsanity.com/paper/2501.10481/) (2025)
- [Bayesian Physics-Informed Neural Networks for Inverse Problems (BPINN-IP): Application in Infrared Image Processing](https://mlsanity.com/paper/2512.02495/) (2025)
- [DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion](https://mlsanity.com/paper/2605.04997/) (2026)
- [The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning](https://mlsanity.com/paper/2610.03225/) (2026)

## Abstract (arXiv)

Geophysical inversion attempts to estimate the distribution of physical properties in the Earth's interior from observations collected at or above the surface. Inverse problems are commonly posed as least-squares optimization problems in high-dimensional parameter spaces. Existing approaches are largely based on deterministic gradient-based methods, which are limited by nonlinearity and nonuniqueness of the inverse problem. Probabilistic inversion methods, despite their great potential in uncertainty quantification, still remain a formidable computational task. In this paper, I explore the potential of deep learning methods for electromagnetic inversion. This approach does not require calculation of the gradient and provides results instantaneously. Deep neural networks based on fully convolutional architecture are trained on large synthetic datasets obtained by full 3-D simulations. The performance of the method is demonstrated on models of strong practical relevance representing an onshore controlled source electromagnetic CO2 monitoring scenario. The pre-trained networks can reliably estimate the position and lateral dimensions of the anomalies, as well as their resistivity properties. Several fully convolutional network architectures are compared in terms of their accuracy, generalization, and cost of training. Examples with different survey geometry and noise levels confirm the feasibility of the deep learning inversion, opening the possibility to estimate the subsurface resistivity distribution in real time.